Lumina

by Lumina
5
4
3
2
1
Score: 56/100

Description

Reviews

No reviews yet.

Stats

14
stars
8,779
downloads
2
forks
113
days
0
days
2
days
0
total PRs
0
open PRs
0
closed PRs
0
merged PRs
13
total issues
0
open issues
13
closed issues
443
commits

Latest Version

2 days ago

Changelog

v1.4.22 — Release Notes

새로운 기능

  • 백업 파일에서 노트 이전 버전을 선택해 복원하는 기능 추가
  • 에디터 퀵 액션 및 자동 백링크 적용 시 인라인 Diff 승인 UI 지원
  • 채팅히스토리 저장경로에 날짜 포맷 커스텀 기능 추가

기능 개선

  • 내장 에이전트 도구를 로컬 HTTP 서버와 분리해 인메모리에서 직접 실행하도록 개선
  • 시맨틱 그래프 유사도 계산을 노트 전체 청크 평균 임베딩(Mean Pooling) 방식으로 개선
  • 인라인 자동완성 시 커서 뒤 문맥을 함께 참조하도록 개선
  • 프론트매터 자동 생성 시 불필요한 lumina* 메타데이터 기록 제거 (AI 태그·요약만 유지)
  • 퀵 액션(replace/append)에 전용 모델 지정을 일관되게 적용하도록 개선
  • Canvas 세부 옵션을 고급 설정으로 이동해 설정 UI 간소화 및 미사용 코드 정리

버그수정

  • 백업 파일 확장자를 .bak으로 변경하여 볼트 내 백링크·태그·그래프 오염 문제 수정
  • 자동 백링크 시 한국어 복합어 훼손 및 동일 노트 중복 링크 생성 문제 수정 (알림 다국어화 포함)
  • 한글/CJK 인라인 자동완성 시 불필요한 선행 공백이 삽입되던 문제 수정
  • 퀵 액션 실행 중 오류 발생 시 에디터 원문이나 커서가 훼손되던 문제 수정
  • 워커 및 폴리필의 동적 Function 호출 제거로 실행 호환성 개선
  • CLI프로바이더로 연결하여 문서 수정 시 백업파일 생성안되던 문제 수정

README file from

Github

Lumina: All-in-One AI Assistant (RAG + MCP + CLI Agents)

Lumina is a powerful all-in-one assistant plugin for Obsidian that transforms your knowledge base into a complete AI hub by combining multi-LLM support (Cloud & Local), terminal CLI agents (Claude Code, Antigravity, OpenCode, Codex), zero-config RAG, bidirectional MCP integration, and autonomous AI agents.

alt text


Main Features

Feature Description
Multi-LLM Chat View A dedicated side panel that understands the context of your notes. Supports everything from powerful cloud models to local LLMs for maximum privacy.
Terminal CLI Agents Integration Run official terminal AI agents (Claude Code, Antigravity, OpenCode, Codex) inside Obsidian's side panel with real-time thinking streams and read/edit safety modes.
Zero-Config RAG Features 100% offline local embeddings to prevent data leaks. Automatically indexes your vault in real-time without complex configurations.
Smart Discovery Instantly finds documents highly relevant to the note currently being written using semantic search, detects and warns about potential duplicates, and inserts recommended tags and related links with a single click.
Inline AI Quick Actions Highlight text in the editor to instantly summarize, translate, or proofread without interrupting your writing flow.
Smart Agent Mode LLMs autonomously plan and execute complex tasks such as note searching, creation, modification, deletion/move, and terminal management using built-in MCP tools.
MCP Integration (Client & Server) A bidirectional, full-stack integration that allows you to use external tools within Obsidian (Client), or let external AIs interact with your notes (Server).

Quick Start

Lumina offers two tracks tailored to your skill level. Choose the one that suits you best!

  1. Install and enable Lumina.
  2. Go to Settings > Lumina and enter your free API key (Gemini or Groq) obtained from the links below.
  3. Open any note and ask Lumina a question in the right sidebar panel. That's it! (Once the local RAG indexing is complete in the side panel, conversations based on your notes will be immediately activated.)
  1. In Settings > Connections, connect your preferred Terminal CLI Agent (Claude Code, Antigravity, OpenCode, Codex), local LLM, or cloud AI.
  2. Select the CLI agent in the side panel chat (with 👁️ Read-Only / ✏️ Edit Mode), or type /mcp to activate Smart Agent Mode.
  3. Issue autonomous commands like, "Find all this week's meeting notes in my vault and compile them into a single summary file."

[!IMPORTANT] Secure API Key Storage All API keys you enter are never stored as plain text files. They are securely encrypted and stored locally via Obsidian's built-in SecretStorage, ensuring your data remains safe.


Detailed Features & Usage (Click to Expand)

  • Description: Instantly converse with various AI models via a dedicated side panel inside Obsidian. Fully supports powerful cloud models like Gemini and Groq, as well as Local LLMs (Ollama, LM Studio, etc.) for absolute privacy.
  • How to use: Click the chat icon on the left ribbon or execute Lumina: Open Chat from the command palette.
  • Pro Tip: Highlight text in the editor, right-click, and use the context menu to directly inject the selected text into the chat as context for your questions!
  • Description: Run and orchestrate terminal AI agents directly inside Obsidian's side panel to explore, analyze, and manage your vault notes.
  • Supported Agents: Anthropic Claude Code, Google Antigravity, OpenCode, and OpenAI Codex.
  • Key Features:
    • Read-Only & Edit Safety Toggle: Switch between 👁️ Read-Only mode (safely inspect and analyze notes without modifying files) and ✏️ Edit mode with a single click in the chat toolbar.
    • Visual Thinking: Streams and displays the agent's internal reasoning process in collapsible real-time thinking blocks.
    • Real-Time Status & Modified Files: Shows tool execution status in real time and provides clickable badges to instantly open files modified by the agent.
    • Active Note & Media Context: Automatically feeds the active note and attached images/files into the CLI prompt for seamless contextual conversations.
    • External Terminal MCP Sync (Optional): Generates configuration files (.claude/mcp.json, opencode.json, codex.json) in your vault so CLI sessions run in your system terminal can also access Lumina's MCP tools.
  • How to use: In Lumina Settings > Connections, select your preferred CLI provider, configure the binary path, and start chatting in the side panel.
  • Description: AI gains deep insight into your knowledge base. It autonomously searches relevant notes during conversations and displays similar documents and recommended tags in the side panel, creating smart contextual links.
  • Offline Security: Lumina's RAG system uses 100% offline local embeddings (built-in ibm-granite multilingual embedding model) to analyze your notes. Unless a cloud model is selected, your valuable note data will never leave your device.
  • Fully Automated: Zero configuration required! Background indexing quietly starts the moment the plugin is enabled, and automatically syncs in real-time (watch mode) whenever notes are modified.
  • Description: Based on the RAG engine, it visualizes information highly relevant to the note currently being written right in the 'Smart Discovery' tab of the sidebar panel.
  • Key Features:
    • Semantic Search: Beyond simple keyword matching, it analyzes the context and meaning of the entered sentence to search for similar notes.
    • Duplicate Document Detection: Displays a warning if a document with highly similar content already exists in your vault to prevent information fragmentation and duplicate writing.
    • Recommended Tags & Related Notes: Analyzes the context of the note being written to suggest appropriate tags and recommend related notes in real-time.
    • One-click Integration & Chat: Insert recommended tags or related notes into your document as tags or markdown links ([[Note Name]]) with a single click, or stage selected notes to immediately start an AI conversation.
  • How to use: Click the chat icon on the left ribbon to open the side panel, and switch to the Smart Discovery tab at the top.
  • Description: Instantly transform text within the markdown editor without breaking your writing flow. Easily handle translation, summarization, grammar correction, and detailed explanations for selected text.
  • How to use: Highlight the text and execute Quick Actions via the inline popup menu or command palette. (Tip: Assign hotkeys in Obsidian settings for lightning-fast access!)
  • Description: When activated, the LLM autonomously determines and orchestrates various built-in MCP tools to perform tasks. It can complete complex, multi-step operations by combining note searching, reading, writing, RAG retrieval, and daily notes integration.
  • Local LLM Support: Implements a dedicated parser that supports text-based tool prompting, allowing the agent to function smoothly even in Local LLM environments, not just with high-performance cloud models.
  • Robust Security & User Control (Human-in-the-Loop): Destructive operations such as content modification, file deletion, or terminal commands cannot be processed by the agent alone. File modifications require inline Diff review in the editor with chunk-by-chunk accept/reject, while sensitive actions like file creation, deletion, or terminal commands require explicit approval via inline approval cards in the chat panel. (Automatic overwrite-protection backups included)
  • Cost Prevention & Limits: Default limits on tool usage count and append character length are applied to prevent AI malfunctions or infinite loops. (These limits can be freely adjusted by the user in advanced settings.)
  • How to use: Type the /mcp command in the chat or use the top icon to open the quick popup and enable 'Agent Mode'. (The internal Lumina server will automatically start as needed to execute tools.)
  • Description: Seamlessly bridges Obsidian with the broader AI ecosystem via the Model Context Protocol (MCP). Use Obsidian as an all-in-one AI hub, or leverage it as your AI's second brain!
  • Client Mode (Obsidian-led):
    • Interact and work directly with AI within Obsidian.
    • Connect numerous external MCP servers (GitHub, local DBs, web search, etc.) to instantly scrape and organize vast amounts of data into your notes.
  • Server Mode (External AI-led):
    • Provides various tools allowing external AI assistants (Claude, Cursor, etc.) or the Agent Mode AI to directly access your vault and the internet.
    • Web Search: `lumina_web_search` (Search the web using various providers like Tavily, Exa, Google with smart truncation to save API costs).
    • Read & Search: read_active_note, read_note (supports line ranges startLine/endLine), search_notes (supports tag filtering), grep_search (regex/text search with line numbers across vault files), glob_files (wildcard file pattern matching, e.g. **/*.md), list_folders (list folders and subfolders), get_outgoing_links (inspect outgoing links & embeds with resolution status), list_tasks (aggregate markdown task items with completion filter), list_notes, rag_search, get_backlinks, get_note_metadata (includes outline headings, links, embeds), list_attachments, list_tags, query_metadata to provide extensive context to the AI.
    • Write & Modify: create_note, append_to_note, replace_note, patch_note (supports atomic batch patches and replaceAll), update_frontmatter (supports smart value parsing and key deletion), save_attachment, create_canvas, generate_moc, auto_link_note (create/modify notes/canvases, generate Map of Content notes, auto-link mentions, and save binary files).
    • Manage & Execute: open_note (instantly open note/file in Obsidian editor tab), delete_note, move_note (move/rename), run_shell_command (execute terminal shell commands on desktop OS), show_notice (display Obsidian UI notifications).
    • Daily Notes: read_daily_note, append_to_daily_note (read/write integration for daily notes with optional date support).
    • External Terminal CLI MCP Sync: Optionally generates local MCP server configs (.claude/mcp.json, opencode.json, codex.json) so CLI tools in external terminals can access Lumina's vault tools.
    • Vault Safety & User Control (Human-in-the-Loop): Sensitive actions require explicit confirmation via inline approval cards, file edits feature editor inline Diff review, and automatic backups are created during file modifications.
  • How to use: Enable MCP features in the plugin settings and configure the client/server transport method (SSE).
  • Note: Lumina comes with multi-layered safety mechanisms including inline Diff review and user approval cards (Human-in-the-Loop), automatic backups during file modifications (overwrite protection), and limits to prevent infinite loops and runaway tool calls. However, since the agent and external AI directly access your vault, we recommend initially monitoring operations closely.

Debug Mode & Bug Reports

You can view all internal data processed by the plugin by enabling Advanced Settings and toggling [Debug Mode] under the [Misc & Extensions] tab in settings. (Debug logs are not saved until downloaded.)

Helpful Information for Resolution:

  • Your OS (Windows, macOS, Linux) and Obsidian version.
  • The AI Provider and Model Name used (e.g., OpenAI / gpt-4o, Ollama / llama3).
  • The log file downloaded after the error occurred in Debug Mode.

[!IMPORTANT] Since log files may contain chat transcripts, please remove any sensitive information before submitting. Report a Bug (GitHub Issues)


Support & Sponsor

Lumina is an open-source project maintained with care and continuously updated. If Lumina has saved you time or improved your workflow, please consider buying a coffee to support ongoing development and maintenance!